Quantifying and simulating the weather forecast uncertainty for advanced building control
Journal of Building Performance Simulation,
Journal Year:
2025,
Volume and Issue:
unknown, P. 1 - 16
Published: Jan. 28, 2025
Language: Английский
Improving Temperature Forecast Accuracy with Enhanced Stacking Operational Consensus Forecasts Algorithm
Published: Jan. 1, 2025
Language: Английский
Applying artificial intelligence to deal with the cold wave
Taḥqīq va tusi̒ah-i salāmata,
Journal Year:
2025,
Volume and Issue:
2(4), P. 37 - 41
Published: Jan. 1, 2025
Language: Английский
Predicting Salinity Levels in the Mekong Delta (Viet Nam): Analysis of Machine Learning and Deep Learning Models
Phong Duc,
No information about this author
Thang Tang Duc,
No information about this author
Giap Pham Van
No information about this author
et al.
Published: April 29, 2025
Abstract
Salinity
intrusion
stands
out
as
a
severe
yet
escalating
challenge
facing
the
water
resource
management
and
agricultural
production
of
Mekong
Delta
in
Vietnam
result
climate
change
upstream
hydrological
changes.
This
paper
assesses
efficacy
six
different
machine
learning
(ML)
deep
models
(DL)
for
hourly
prediction
salinity
at
four
stations
(Cau
Quan,
Tra
Vinh,
Ben
Trai,
Tran
De).
The
are
XGB,
GB,
SVR,
LSTM,
RNN
ANN.
Using
data
2015–2020
with
discharge
tidal
levels
major
inputs
we
designed
training
testing
(training:
Jan
2015-mid
2018;
testing:
mid
2018-Feb
2020).
Our
results
prove
that
LSTM
XGB
have
best
prediction.
In
particular,
they
showed
good
accuracy
predicting
(RMSE:
0.25
to
0.30,
R
2
>
0.97)
downstream
1.5
1.6,
0.88).
success
is
due
capacity
high
temporal
resolution
well
spatio-temporal
dynamics
variation.
structure
has
proven
be
effective
capturing
long-term
dependencies,
such
seasonal
patterns,
while
successfully
non-linear
interactions
between
greatest
success,
particularly
discharge-tidal
level
interactions.
ML/DL
capable
forecasting
which
can
open
doors
data-driven
Delta.
Future
studies
should
further
add
hydro-meteorological
parameters,
other
hybrid
architectures,
real-time
systems,
could
useful
operationally
wider
applicability.
Language: Английский
An Empirical Analysis of Deep Learning Models for Temperature Prediction
International Journal of experimental research and review,
Journal Year:
2025,
Volume and Issue:
47, P. 12 - 24
Published: April 30, 2025
Accurate
temperature
prediction
is
critical
in
diverse
areas,
such
as
agriculture,
disaster
management,
and
urban
planning,
where
understanding
climatic
patterns
essential.
This
study
explores
the
application
of
advanced
deep-learning
models
for
forecasting,
focusing
on
model’s
ability
to
establish
complex
relationships
temporal
dependencies
within
data.
evaluates
performance
various
using
environmental
Long
Short-Term
Memory
(LSTM),
Gated
Recurrent
Unit
(GRU),
Bidirectional
LSTM
(BiLSTM),
GRU
(BiGRU)
were
developed
compared.
The
trained
meteorological
data
from
Ranchi,
India,
spanning
2014-2024.
Performance
was
assessed
Root
Mean
Square
Error
(RMSE),
loss
function
analysis,
statistical
significance
testing.
Results
indicate
that
bidirectional
architectures
(BiLSTM
BiGRU)
consistently
outperformed
unidirectional
models.
BiLSTM
achieved
lowest
RMSE
most
balanced
values
across
training,
validation
test
sets.
model
performed
well
by
39.19.7%
15.36%
loss.
From
best
performer
compared
with
BiGRU,
a
negative
t-statistic
(-29.65)
very
low
p-value
(0.00000771),
indicating
statistically
significant
difference.
Language: Английский
Quantification and Prediction of the Impact of ENSO on Rainfed Rice Yields in Thailand
Usa Humphries Wannasingha,
No information about this author
Muhammad Waqas,
No information about this author
Shakeel Ahmad
No information about this author
et al.
Environmental Challenges,
Journal Year:
2025,
Volume and Issue:
unknown, P. 101123 - 101123
Published: March 1, 2025
Language: Английский
Investigation of Precipitation and Temperature Trends Using Classical and Innovative Approaches with Corresponding Frequencies in Antalya Basin, Türkiye.
Cansu Ercan,
No information about this author
Ahmad Abu Arra,
No information about this author
Eyüp Şişman
No information about this author
et al.
Physics and Chemistry of the Earth Parts A/B/C,
Journal Year:
2025,
Volume and Issue:
unknown, P. 103958 - 103958
Published: May 1, 2025
Language: Английский
Study on the inversion and spatiotemporal variation mechanism of soil salinization at multiple depths in typical oases in arid areas: A case study of Wei-Ku Oasis
Agricultural Water Management,
Journal Year:
2025,
Volume and Issue:
315, P. 109542 - 109542
Published: May 10, 2025
Language: Английский